Skip to main content
Glama
Kitchen Pass MCP server

Kitchen Pass MCP server

Official

Why did this dish go wrong (paid, $0.02)

diagnose_cooking_problem
Destructive

Identify cooking faults by sending a dish and a symptom; receive the likely cause and a chef-provided fix.

Instructions

Why is my cake dense? Mayo split? Steak tough? Send a dish and a symptom; get the likely cause and head chef Cristopher's verified fix. Over 50 problems: bread, pizza dough, cheesecake, pavlova, macarons, choux, croissants, pastry, cookies, brownies, ganache, hollandaise, mayo, gravy, risotto, rice, stock, curry, steak, mince, fried fish, poached eggs. Refused, never guessed: allergens, storage, leftovers, reheating, safe temperatures. Only a 200 answer is charged; refusals and 404s are free.

Send the dish and a short symptom in the user's words ("dense", "split", "came out gluey"). Leave out extra clauses ("…after I added the butter"). Rescue questions ("can I save it?") aren't answered, and "is it still safe?" is refused. An unlisted dish or symptom gets a free 404 with the valid names. Retry only if the user's dish really is one of them; don't swap in a different dish. Costs $0.02. Paid automatically in USDC with x402 (test USDC when this server is set to base-sepolia), within this server's per-session and per-day spend caps. Only a 200 answer is charged; 400, 404 and 422 are free. Set dryRun to true to check for free whether this would be answered and what it costs; nothing is signed. If unsure what is covered, call check_coverage first (free). Not every answer is chef-verified: say "chef-verified by Cristopher" only when the result's label says exactly that; otherwise say it is not chef-verified. A refusal is final: don't rephrase the question to get around it.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "dish": "<dish>",
      "symptom": "<symptom>"
    },
    "name": "diagnose_cooking_problem"
  }
}

Input Schema

NameRequiredDescriptionDefault
dishYes
dryRunNoFree quote only: check whether this would be answered and what it costs. Nothing is signed or charged.
symptomYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only flag it as a paid mutation (destructiveHint=true, openWorldHint=true); the description goes further and explains the billing model ($0.02 in USDC via x402, charged only on 200, free on 400/404/422, spend caps), that dryRun signs nothing, and that refusals are final. It also discloses result labeling so the agent doesn't overstate chef verification.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with concrete examples and organized by concern, but the charging rule is stated twice ('Only a 200 answer is charged; refusals and 404s are free' appears near-verbatim in two places), which is redundant for a description this dense.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, yet the description still tells the agent what comes back (cause, fix, verification label) and its failure modes (404 with valid names, refusal). For a paid, network-touching tool with only three parameters, nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33% (only dryRun is documented), but the description compensates fully: it defines what to put in dish, how to phrase the symptom in the user's own words, and gives worked examples plus anti-patterns (omit extra clauses like '…after I added the butter').

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (diagnose a dish from a symptom), gives the input contract (dish + symptom) and the output (likely cause + chef's fix). It clearly separates itself from siblings like check_coverage and get_sample_answer by covering the paid diagnosis path.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit about when to use (specific dish + short symptom), when not to (rescue/salvage questions, safety questions), what to do first if coverage is unclear (check_coverage, free), and how to handle a 404 (retry only if the dish truly matches). Also names the dryRun preview as a free alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.